数学科学学院学术报告[2024]045号
(高水平大学建设系统报告925号)
报告题目:An Enhanced Gromov-Wasserstein Barycenter Method for Graph-based clustering
主讲人:张振 副教授(南方科技大学)
报告时间:2024年6月4日上午9:00-10:00
报告地点:汇星楼514
内容摘要:Gromov-Wasserstein Learning (GWL) has recently introduced a framework for graph partitioning by minimizing the Gromov-Wasserstein (GW) distance. Various improved versions stemming from this framework have showcased the state-of-the-art (SOTA) performance on clustering tasks. Building upon GW barycenter, we introduce a novel approach that significantly enhances other GW-based models flexibility by relaxing the target distribution (cluster size) in GWL and using a wide class of positive semi-definite matrices. We then develop an efficient algorithm to solve the resulting non-convex problem by utilizing regularization and the successive upper-bound minimization techniques. The proposed method exhibits the capacity to identify improved partitioning results within an enriched searching space, as validated by our developed theoretical framework and numerical experiments. Real data experiments illustrate our method outperforms the SOTA graph partitioning methods on both directed and undirected graphs.
报告人简介:南方科技大学数学系副教授(博士生导师)。本科毕业于中国科学技术大学数学系,之后进入香港科技大学学习并于2013年获得应用数学博士学位,师从王筱平教授。他于2013年至2015年在新加坡国立大学从事计算数学的博士后研究,并在2015年加入了南方科技大学数学系,青年千人。他的主要研究领域在于应用问题的建模和计算,特别是数值偏微分方程,多相复杂流模型,以及高维数据分析。
欢迎师生参加!
报告邀请人:张露婵
数学科学学院
2024年6月4日